Learning Gated Bayesian Networks for Algorithmic Trading
2014 (English)In: Probabilistic Graphical Models: 7th European Workshop, PGM 2014, Utrecht, The Netherlands, September 17-19, 2014. Proceedings / [ed] Linda C. van der Gaag and Ad J. Feelders, Springer, 2014, 49-64 p.Conference paper (Refereed)
Gated Bayesian networks (GBNs) are a recently introduced extension of Bayesian networks that aims to model dynamical systems consisting of several distinct phases. In this paper, we present an algo- rithm for semi-automatic learning of GBNs. We use the algorithm to learn GBNs that output buy and sell decisions for use in algorithmic trading systems. We show how using the learnt GBNs can substantially lower risks towards invested capital, while at the same time generating similar or better rewards, compared to the benchmark investment strat- egy buy-and-hold.
Place, publisher, year, edition, pages
Springer, 2014. 49-64 p.
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 8754
Probabilistic graphical models, Bayesian networks, algorithmic trading, decision support
IdentifiersURN: urn:nbn:se:liu:diva-110777DOI: 10.1007/978-3-319-11433-0_4ISI: 000358253800004ISBN: 978-3-319-11432-3 (print)ISBN: 978-3-319-11433-0 (online)OAI: oai:DiVA.org:liu-110777DiVA: diva2:748876
7th European Workshop on Probabilistic Graphical Models, (PGM 2014), Utrecht, The Netherlands, September 17-19, 2014